Файловый менеджер - Редактировать - /home/digitalm/venv/lib/python3.7/site-packages/pandas/core/groupby/__pycache__/generic.cpython-37.pyc
Назад
B �5�g�� � @ s@ d Z ddlmZ ddlmZmZ ddlmZ ddlm Z ddl m Z m Z m Z mZmZmZmZ ddlZddlZddlmZmZ dd lmZmZm Z m Z dd l m Z m Z m!Z! dd l"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z)m*Z* dd l+m,Z,m-Z- dd l.m/Z/m0Z0 ddl1m2Z2m3Z3m4Z4 ddl5m6Z6 ddl7m8Z8 ddl9m: m;Z< ddl=m>Z> ddl?m@Z@ ddlAmBZB ddlCmDZD ddlEmFZFmGZGmHZHmIZImJZJ ddlKmLZLmMZMmNZN ddlOmPZP ddlQmRZR ddlSmTZT eddd g�ZUeeVe d e f f ZWed �ZXd d d!�d"d#�ZYd d$d%�d&d'�ZZeZePeDj[�G d(d)� d)eFeP ��Z\eZe@eDj]�G d*d+� d+eFe@ ��Z^dS ),z� Define the SeriesGroupBy and DataFrameGroupBy classes that hold the groupby interfaces (and some implementations). These are user facing as the result of the ``df.groupby(...)`` operations, which here returns a DataFrameGroupBy object. � )� annotations)�abc� namedtuple)�partial)�dedent)�Any�Callable�Hashable�Iterable�Mapping�TypeVar�UnionN)�lib� reduction)� ArrayLike� FrameOrSeries�FrameOrSeriesUnion� Manager2D)�Appender� Substitution�doc)� ensure_int64�is_bool�is_categorical_dtype� is_dict_like�is_integer_dtype�is_interval_dtype�is_numeric_dtype� is_scalar)�isna�notna)� algorithms�nanops)�maybe_mangle_lambdas�reconstruct_func�validate_func_kwargs)� GroupByApply)�SpecificationError)�!create_series_with_explicit_dtype)� DataFrame)�NDFrame)�base)�GroupBy� _agg_template� _apply_docs�_transform_template�group_selection_context)�Index� MultiIndex�all_indexes_same)�Series)�maybe_use_numba)�boxplot_frame_groupby�NamedAgg�columnZaggfunc.� ScalarResult�strztype[FrameOrSeries])�name�klassc s0 � fdd�}t |� �}|jp d|_� |_t|�S )z� Create a property for a GroupBy subclass to dispatch to DataFrame/Series. Parameters ---------- name : str klass : {DataFrame, Series} Returns ------- property c s | � � �S )N)Z _make_wrapper)�self)r; � �Q/home/digitalm-up/venv/lib/python3.7/site-packages/pandas/core/groupby/generic.py�propt s z generate_property.<locals>.prop� )�getattr�__doc__�__name__�property)r; r< r@ Z parent_methodr> )r; r? �generate_propertyf s rF zfrozenset[str])r< � allowlistc s � �fdd�}|S )a� Create GroupBy member defs for DataFrame/Series names in a allowlist. Parameters ---------- klass : DataFrame or Series class class where members are defined. allowlist : frozenset[str] Set of names of klass methods to be constructed Returns ------- class decorator Notes ----- Since we don't want to override methods explicitly defined in the base class, any such name is skipped. c s4 x.� D ]&}t | |�rqt|��}t| ||� qW | S )N)�hasattrrF �setattr)�clsr; r@ )rG r< r> r? �pinner� s z*pin_allowlisted_properties.<locals>.pinnerr> )r< rG rK r> )rG r< r? �pin_allowlisted_properties} s rL c s� e Zd ZejZdd�dd�Zed�Ze e d j de d d ��� fd d ��Z e eed d �dMddd�dd��ZeZdd�dd�ZdNddddd�dd �Zd d d �d d �Zd d d �d!d"�ZdOd d$d%dd&d'�d(d)�Zd*d+� Zed d,�e e�ddd�d-d.���ZdPdddd1�d2d3�Zdd d4�d5d6�Zdd�d7d8�Z d d d9�d:d;�Z dQdd<�d=d>�Z dRdd d?�d@dA�Z e e j!�dBdC� �Z!dSdddddD�dEdF�Z"d d�dGdH�Z#dTdKdL�Z$� Z%S )U� SeriesGroupByzIterable[Series])�returnc c s | j V d S )N)� _selected_obj)r= r> r> r? �_iterate_slices� s z SeriesGroupBy._iterate_slicesa� Examples -------- >>> s = pd.Series([1, 2, 3, 4]) >>> s 0 1 1 2 2 3 3 4 dtype: int64 >>> s.groupby([1, 1, 2, 2]).min() 1 1 2 3 dtype: int64 >>> s.groupby([1, 1, 2, 2]).agg('min') 1 1 2 3 dtype: int64 >>> s.groupby([1, 1, 2, 2]).agg(['min', 'max']) min max 1 1 2 2 3 4 The output column names can be controlled by passing the desired column names and aggregations as keyword arguments. >>> s.groupby([1, 1, 2, 2]).agg( ... minimum='min', ... maximum='max', ... ) minimum maximum 1 1 2 2 3 4 .. versionchanged:: 1.3.0 The resulting dtype will reflect the return value of the aggregating function. >>> s.groupby([1, 1, 2, 2]).agg(lambda x: x.astype(float).min()) 1 1.0 2 3.0 dtype: float64�templateZseriesZseries_examples)�input�examplesc s t � j|f|�|�S )N)�super�apply)r= �func�args�kwargs)� __class__r> r? rU � s zSeriesGroupBy.applyr4 )rS r< N)�engine� engine_kwargsc O sh t |�r^t| �� | j}W d Q R X | j|�� |f|�d|i|��\}}| jj|�� ||jd�S |d k} d } | r~t |�\} }i }t |t �r�t | |�||�S t |t j�r�t|�}| �|�} | r�| | _| S t�|�} | r�|s�|s�t | | �� S | jjdk�r| j|f|�|�S y| j|f|�|�S tk �rb | j|f|�|�}tt|�| jjd d�}t ||t d�S X d S )Nr[ )�indexr; � r )r; )r\ �dtype_if_empty) r5 r0 rO �_aggregate_with_numbaZto_frame�obj� _constructorZravelr; r% � isinstancer: rB r r r# �_aggregate_multiple_funcs�columns�comZget_cython_func�grouper�nkeys�_python_agg_general�KeyError�_aggregate_namedr1 �sorted�namesr( �object) r= rV rZ r[ rW rX �data�resultr\ � relabelingrd �retZcyfuncr> r> r? � aggregate� s> zSeriesGroupBy.aggregater) c C s6 t |t�rtd��n^tdd� |D ��rBdd� |D �}tt|� �}n0g }x |D ]}|�t�|�p`|� qLW t||�}i }x4t |�D ](\}\}}t j ||d�}| � |�||< q�W tdd� |� � D ��r�dd lm} | |� � d d d� |�� D �d �} | S d d� |�� D �} | jj| d d�} tdd� |D ��| _| �| �} | S )Nz nested renamer is not supportedc s s | ]}t |ttf�V qd S )N)rb �tuple�list)�.0�xr> r> r? � <genexpr> s z:SeriesGroupBy._aggregate_multiple_funcs.<locals>.<genexpr>c S s& g | ] }t |ttf�s ||fn|�qS r> )rb rs rt )ru rv r> r> r? � <listcomp> s z;SeriesGroupBy._aggregate_multiple_funcs.<locals>.<listcomp>)�label�positionc s s | ]}t |t�V qd S )N)rb r) )ru rv r> r> r? rw 1 s r )�concatr] c S s g | ] }|j �qS r> )ry )ru �keyr> r> r? rx 5 s )�axis�keysc S s i | ]\}}||j �qS r> )rz )ru r| �valr> r> r? � <dictcomp>; s z;SeriesGroupBy._aggregate_multiple_funcs.<locals>.<dictcomp>)r\ c s s | ] }|j V qd S )N)ry )ru r| r> r> r? rw = s )rb �dictr' �any�next�zip�appendre Zget_callable_name� enumerater+ Z OutputKeyrr �valuesZpandasr{ r~ �itemsr` �_constructor_expanddimr1 rd �_reindex_output) r= �argrd �f�results�idxr; rV r| r{ �res_df�indexed_output�outputr> r> r? rc s. z'SeriesGroupBy._aggregate_multiple_funcs���r: r �bool�int)�how�alt� numeric_only� min_countc s� �j }|j}|j�|r:t|j�s:tt��j� d�� d���ddd�� ����fdd� }||�}�jj |�j j |j d�} �� | �S )N�.z! does not implement numeric_only.r )r� rN c sL y �j jd| ��jd �d�}W n& tk rF �j| �j� d�}Y nX |S )Nrr r] )r} r� )�ndimr� )rf �_cython_operationr� �NotImplementedError�_agg_py_fallback)r� ro )r� rn r� r� r= r> r? � array_funcR s z5SeriesGroupBy._cython_agg_general.<locals>.array_func)r\ r; )rO �_values�_mgrr �dtyper� �typerD r` ra rf � result_indexr; r� ) r= r� r� r� r� r` Zobjvalsr� ro �serr> )r� rn r� r� r= r? �_cython_agg_generalB s z!SeriesGroupBy._cython_agg_generalz+Mapping[base.OutputKey, Series | ArrayLike])r� rN c C sL t |�dkst�| jj}| jj}tt|�� ��}| jj |||d�}| � |�S )a� Wraps the output of a SeriesGroupBy aggregation into the expected result. Parameters ---------- output : Mapping[base.OutputKey, Union[Series, ArrayLike]] Data to wrap. Returns ------- Series Notes ----- In the vast majority of cases output will only contain one element. The exception is operations that expand dimensions, like ohlc. r] )r\ r; ) �len�AssertionErrorr` r; rf r� r� �iterr� ra r� )r= r� r; r\ r� ro r> r> r? �_wrap_aggregated_outputg s z%SeriesGroupBy._wrap_aggregated_outputc C sP t |�dkst�| jj}tt|�� ��}| jj|| jj|d�}t |t �sLt�|S )a Wraps the output of a SeriesGroupBy aggregation into the expected result. Parameters ---------- output : dict[base.OutputKey, Union[Series, np.ndarray, ExtensionArray]] Dict with a sole key of 0 and a value of the result values. Returns ------- Series Notes ----- output should always contain one element. It is specified as a dict for consistency with DataFrame methods and _wrap_aggregated_output. r] )r\ r; ) r� r� r` r; r� r� r� ra r\ rb r4 )r= r� r; r� ro r> r> r? �_wrap_transformed_output� s z&SeriesGroupBy._wrap_transformed_outputFr1 zlist[Any] | Noner )rn r~ r� �not_indexed_samerN c s� t � �dkr*�jjg �jj�jj|jd�S |dk s6t�dd�� �fdd� }t|d t �r�|� }�jj ||d�}�� |�}|j �j d �}�jj|_|S t|d ttf�r��j� ||d �S �jj||� �jjd �} �� | �S dS ) a Wrap the output of SeriesGroupBy.apply into the expected result. Parameters ---------- data : Series Input data for groupby operation. keys : Index Keys of groups that Series was grouped by. values : Optional[List[Any]] Applied output for each group. not_indexed_same : bool, default False Whether the applied outputs are not indexed the same as the group axes. Returns ------- DataFrame or Series r )r; r\ r� Nr1 )rN c s8 �j jdkr tj� �j jd�} nt� �j jd d�} | S )Nr] )rl r )r; )rf rg r2 � from_tuplesrl r1 )r\ )r~ r= r> r? � _get_index� s z6SeriesGroupBy._wrap_applied_output.<locals>._get_index)r\ )�dropna)r� )rn r\ r; )r� r` ra r; rf r� r� r� rb r� r� r� �stack�observedr4 r) �_concat_objects) r= rn r~ r� r� r� r\ r� Zres_serro r> )r~ r= r? �_wrap_applied_output� s( z"SeriesGroupBy._wrap_applied_outputc O sd i }d}xV| D ]N\}}t �|d|� ||f|�|�}t�|�}|sTt�||j� d}|||< qW |S )NFr; T)rm � __setattr__� libreductionZextract_resultZcheck_result_arrayr� ) r= rV rW rX ro Z initializedr; �groupr� r> r> r? rj � s z SeriesGroupBy._aggregate_named)r< c O s | j |f|�||d�|��S )N)rZ r[ )� _transform)r= rV rZ r[ rW rX r> r> r? � transform� s zSeriesGroupBy.transformTr )r� r� r} c K s� |dks t �| j}y | jjd|j||f|�}W n: tk rh } z t|� d|j� d��|�W d d }~X Y nX |j|| j j |j d�S )Nr r� z is not supported for z dtype)r\ r; ) r� rO rf r� r� r� � TypeErrorr� ra r` r\ r; )r= r� r� r} rX r` ro �errr> r> r? �_cython_transform� s *z SeriesGroupBy._cython_transform)rV rN c O s� t |�s t�t| j�}g }xB| D ]:\}}t�|d|� ||f|�|�}|�|||jd�� q W |r�ddlm } | |�} | � | �} n| jj t j d�} | jj| _| S )z2 Transform with a callable func`. r; )r\ r )r{ )r� )�callabler� r� r` rm r� r� r\ �pandas.core.reshape.concatr{ �_set_result_index_orderedra �npZfloat64r; ) r= rV rW rX r< r� r; r� �resr{ � concatenatedro r> r> r? �_transform_general s z SeriesGroupBy._transform_generalc C s dS )NTr> )r= ro r> r> r? �_can_use_transform_fast* s z%SeriesGroupBy._can_use_transform_fast)ro rN c C sH | j j\}}}|j| j jdd�}t�|j|�}| jj|| jj | jj d�S )zf fast version of transform, only applicable to builtin/cythonizable functions F)�copy)r\ r; ) rf � group_info�reindexr� r! Ztake_ndr� r` ra r\ r; )r= ro �ids�_�outr> r> r? �_wrap_transform_fast_result- s z)SeriesGroupBy._wrap_transform_fast_result)r� c s� t �t�r � ��fdd��n� ��fdd��dd��fdd� �y��fdd ��D �}W n0 ttfk r� } ztd �|�W d d }~X Y nX ��||�}|S ) ao Return a copy of a Series excluding elements from groups that do not satisfy the boolean criterion specified by func. Parameters ---------- func : function To apply to each group. Should return True or False. dropna : Drop groups that do not pass the filter. True by default; if False, groups that evaluate False are filled with NaNs. Notes ----- Functions that mutate the passed object can produce unexpected behavior or errors and are not supported. See :ref:`gotchas.udf-mutation` for more details. Examples -------- >>> df = pd.DataFrame({'A' : ['foo', 'bar', 'foo', 'bar', ... 'foo', 'bar'], ... 'B' : [1, 2, 3, 4, 5, 6], ... 'C' : [2.0, 5., 8., 1., 2., 9.]}) >>> grouped = df.groupby('A') >>> df.groupby('A').B.filter(lambda x: x.mean() > 3.) 1 2 3 4 5 6 Name: B, dtype: int64 Returns ------- filtered : Series c s t | ��� ��S )N)rB )rv )rW rV rX r> r? �<lambda>[ � z&SeriesGroupBy.filter.<locals>.<lambda>c s �| f� ���S )Nr> )rv )rW rV rX r> r? r� ] r� r� )rN c s � | �}|ot |�S )N)r )rv �b)�wrapperr> r? �true_and_notna` s z,SeriesGroupBy.filter.<locals>.true_and_notnac s" g | ]\}}�|�r� � |��qS r> )r� )ru r; r� )r= r� r> r? rx f s z(SeriesGroupBy.filter.<locals>.<listcomp>z'the filter must return a boolean resultN)rb r: � ValueErrorr� � _apply_filter)r= rV r� rW rX �indicesr� �filteredr> )rW rV rX r= r� r� r? �filter7 s # zSeriesGroupBy.filter)r� rN c C s� | j j\}}}| jj}tj|dd�\}}t�||f�}|| }|| }tjddt� |dd� |dd� k�d f }tjd|dd� |dd� kf }|dk} |r�d||< d|| < n&d|| tjd| dd� f @ < d||< tj � ||�j ddd�} t |��r.|d dk�r(| dd� } |t�|� }n| } n | dd� } | j j} t | �t | �k�rztjt | �| jd �| } } | | || < | jj| | | jjd �} | j| dd �S ) z� Return number of unique elements in the group. Returns ------- Series Number of unique values within each group. F)�sortr r] Nr� �int64)r� )r� )r\ r; )� fill_value)rf r� r` r� r! � factorizer� �lexsort�r_�nonzero�add�reduceat�astyper� Z flatnonzeror� �zerosr� ra r; r� )r= r� r� r� r �codes�sorterr� �inc�maskr� r� �riro r> r> r? �nuniquen s6 0" zSeriesGroupBy.nuniquec s* | � � fdd��}| jdkr"|jS |�� S )Nc s | j f � �S )N)�describe)rv )rX r> r? r� � r� z(SeriesGroupBy.describe.<locals>.<lambda>r] )rU r} �TZunstack)r= rX ro r> )rX r? r� � s zSeriesGroupBy.describe)� normalizer� � ascendingr� c ! s� ddl m} ddlm} �jj\}} } �jj} � ���� fdd�} �d k r\t� ��sl| � S nt | j �rl| � S |dk�|� | � }} �d kr�t j | dd�\} } d d � }n8|t| ��dd �} | jj} | j| jjd| jd �} d d � }t| j ��rt�| j| j|f�}nt�| |f�}|| | | }} dt�|dd � |d d� k�d }tjd|f }t|��sf|}|| tdd ��|| td d��k}tjd|f }t| ��s�|}d||< t� t�tj|df �d �}t tj tj � ||�d���jj!}�fdd�|D �|| |�g }dd� �jj"D �| g }�jj#�jj$g }|�rn|d dk���%� �rRd}n |� �fdd�|D � }}��r�|�&d�}t� tj|t|�f �}|�r�|| dk }tj �'||d� �|�� }n�|�}|| }� �r4�d k�r4|�r�|| � n|| }t�� �r|n| |f�}|| |d | }|d< �d k �r�tj(t|�dd��x<|d d� D ],} �tjd| dd � | d d� kf O ��q^W ��)� t|d � } �t� t�*| ���t�+t�*��| �g} ��,� d |d g} || | ddd�\} }t�-|dk|| d�}� �rDt�� �r|n| | d f�}|| | d | }| d< ddd���fd d � ��fd d�|d d� D �}|�.| d � t/|||dd �} t0|j ��r�t1|�}�jj2|| �jj$d �S )!Nr )�get_join_indexers)�cutc s �j tj��� �d�S )N)r� r� r� �bins)rU r4 � value_countsr> )r� r� r� r= r� r> r? �apply_series_value_counts� s z=SeriesGroupBy.value_counts.<locals>.apply_series_value_countsr� T)r� c S s | | S )Nr> )�labr� r> r> r? r� � r� z,SeriesGroupBy.value_counts.<locals>.<lambda>)Zinclude_lowest)Z allow_fillr� c S s | | j jd S )Nr� )Z _multiindexr� )r� r� r> r> r? r� � r� r] )Zrepeatsc s g | ] }� |��qS r> r> )ru � level_codes)�repr> r? rx s z.SeriesGroupBy.value_counts.<locals>.<listcomp>c S s g | ] }|j �qS r> )Z group_index)ru Zpingr> r> r? rx s Fc s g | ] }|� �qS r> r> )ru r� )r� r> r? rx s �floatr� )r� �left)r� r� z np.ndarray)� lev_codesrN c s t �| � ��S )N)r� �repeat)r� )�diff�nbinr> r? � build_codes4 s z/SeriesGroupBy.value_counts.<locals>.build_codesc s g | ] }� |��qS r> r> )ru r� )r� r> r? rx 7 s )�levelsr� rl �verify_integrity)r\ r; )3Zpandas.core.reshape.merger� Zpandas.core.reshape.tiler� rf r� r` r� r� �iterabler r� r! r� r4 �cat� categories�taker� Z _na_valuer r� r� �rightr� r� r� �slicer� r r� r� r� Zreconstructed_codes� groupingsrl r; �allr� �atr� �sumZarangeZtileZcumsum�wherer� r2 r r ra )!r= r� r� r� r� r� r� r� r� r� r r� r� �levZllabr� Z idchangesr� Zlchangesr� r� r� r� rl �d�m�accr� r� Zncatr� r� �mir> ) r� r� r� r� r� r� r� r� r= r� r? r� � s� & ,$ zSeriesGroupBy.value_countsc C sl | j j\}}}| jj}|dkt|� @ }|p.d}tj|| |d�}| jj|| j j| jj dd�}| j |dd�S )z� Compute count of group, excluding missing values. Returns ------- Series Count of values within each group. r� r )� minlengthr� )r\ r; r� )r� ) rf r� r` r� r r� Zbincountra r� r; r� ) r= r� r� �ngroupsr r� r r� ro r> r> r? �count@ s zSeriesGroupBy.countr] �padc sd �r | � � ���fdd��S � dkr,d� d�t| � ��d�}|�| jj�}|j��d�}|| d S ) z=Calculate pct_change of each value to previous entry in groupc s | j �� ��d�S )N)�periods� fill_method�limit�freq)� pct_change)rv )r r r r r> r? r� ] s z*SeriesGroupBy.pct_change.<locals>.<lambda>Nr r )r )r r r] )rU rB �groupbyrf r� �shift)r= r r r r ZfilledZfill_grpZshiftedr> )r r r r r? r X s zSeriesGroupBy.pct_change)N)r� )F)Tr )T)T)FTFNT)r] r NN)&rD � __module__� __qualname__r+ �series_apply_allowlist�_apply_allowlistrP r �_agg_examples_docr r. �formatrU r r- rr �aggrc r� r� r� r� rj r r/ r� r� r� r� r� r� r� r4 r� r� r r � __classcell__r> r> )rY r? rM � sD . 2-$ #8 75 rM c s e Zd ZejZed�Zee edd�d^ddd�dd��Z e Z dd �d d �Z d_d ddddd�dd�Z dd �dd�Zdd �dd�Zd`dd�Zddd d �d d �Zdad dddd"�d#d$�Zd%d&� Zedd'�ee�ddd�d(d)���Zdd �d*d+�Zddd,�d-d.�Zd/d0� Zdddd1�d2d3�Zddd4�d5d6�Z dbd7d8�Z d9d �� fd:d;� Z dcdd<�d=d>�Z d?d �d@dA�Z ddBd,�dCdD�Z!dEddF�dGdH�Z"dEddF�dIdJ�Z#d?ddK�dLdM�Z$dNdO�dPdQ�Z%dNdd4�dRdS�Z&dd �dTdU�Z'dddddV�dWdX�Z(ee)j*j+�deddY�dZd[��Z*ee)j,j+�dfddY�d\d]��Z,e-Z.� Z/S )g�DataFrameGroupBya Examples -------- >>> df = pd.DataFrame( ... { ... "A": [1, 1, 2, 2], ... "B": [1, 2, 3, 4], ... "C": [0.362838, 0.227877, 1.267767, -0.562860], ... } ... ) >>> df A B C 0 1 1 0.362838 1 1 2 0.227877 2 2 3 1.267767 3 2 4 -0.562860 The aggregation is for each column. >>> df.groupby('A').agg('min') B C A 1 1 0.227877 2 3 -0.562860 Multiple aggregations >>> df.groupby('A').agg(['min', 'max']) B C min max min max A 1 1 2 0.227877 0.362838 2 3 4 -0.562860 1.267767 Select a column for aggregation >>> df.groupby('A').B.agg(['min', 'max']) min max A 1 1 2 2 3 4 Different aggregations per column >>> df.groupby('A').agg({'B': ['min', 'max'], 'C': 'sum'}) B C min max sum A 1 1 2 0.590715 2 3 4 0.704907 To control the output names with different aggregations per column, pandas supports "named aggregation" >>> df.groupby("A").agg( ... b_min=pd.NamedAgg(column="B", aggfunc="min"), ... c_sum=pd.NamedAgg(column="C", aggfunc="sum")) b_min c_sum A 1 1 0.590715 2 3 0.704907 - The keywords are the *output* column names - The values are tuples whose first element is the column to select and the second element is the aggregation to apply to that column. Pandas provides the ``pandas.NamedAgg`` namedtuple with the fields ``['column', 'aggfunc']`` to make it clearer what the arguments are. As usual, the aggregation can be a callable or a string alias. See :ref:`groupby.aggregate.named` for more. .. versionchanged:: 1.3.0 The resulting dtype will reflect the return value of the aggregating function. >>> df.groupby("A")[["B"]].agg(lambda x: x.astype(float).min()) B A 1 1.0 2 3.0r) )rS r< N)rZ r[ c O s� t |�rVt| �� | j}W d Q R X | j||f|�d|i|��\}}| jj|||jd�S t|f|�\} }} } t|�}t | |||�} | � � }t |�s�|d k r�|S | r�|d k r�|j d d �| f }| |_|d k�r�| j jdkr�| j|f|�|�S |s�|�r| j|f|�|�}n�| jdk�r | �|�}|S t | |gdi d�} y | � � }W n> tk �r| } z dt|�k�rb� | �|�}W d d }~X Y nRX | j}t|t��r�| jj�� |_n.|jj|jjtt|jj ��d� |j� d�|_| j �s�| � |� t tt!|���|_"|j#d d �S ) Nr[ )r\ rd r] r> )rW rX z no results)�levelr� T)�datetime)$r5 r0 rO r_ r` ra rd r$ r# r& r r �ilocrf rg rh �_aggregate_framer} r� r: rb r4 �_obj_with_exclusionsr� � _set_namesrl rt �range�nlevelsZ droplevel�as_index� _insert_inaxis_grouper_inplacer1 r� r\ �_convert)r= rV rZ r[ rW rX rn ro r\ rp rd �order�opZgbar� Zsobjr> r> r? rr � sP zDataFrameGroupBy.aggregatezIterable[Series])rN c c s` | j }| jdkr|j}t|t�r4|j| jkr4|V n(x&|�� D ]\}}|| jkrRq>|V q>W d S )Nr] )rO r} r� rb r4 r; � exclusionsr� )r= r` ry r� r> r> r? rP s z DataFrameGroupBy._iterate_slicesr� r: r r� r� )r� r� r� r� rN c s� �� � �|r�jdd��ddd�� ����fdd� }�j|dd�}t|�t��k r|tjd t��j� d �� d �� d �td d� �� |�S )NF)r� r )r� rN c sL y �j jd| ��jd �d�}W n& tk rF �j| �j� d�}Y nX |S )Nrr r] )r} r� )r� r� )rf r� r� r� r� )r� ro )r� rn r� r� r= r> r? r� * s z8DataFrameGroupBy._cython_agg_general.<locals>.array_funcT)�ignore_failuresz Dropping invalid columns in r� zQ is deprecated. In a future version, a TypeError will be raised. Before calling .z=, select only columns which should be valid for the function.� )� stacklevel) �_get_data_to_aggregate�get_numeric_data�grouped_reducer� �warnings�warnr� rD � FutureWarning�_wrap_agged_manager)r= r� r� r� r� r� �new_mgrr> )r� rn r� r� r= r? r� s z$DataFrameGroupBy._cython_agg_generalc O s� | j jdkrtd��| j}i }| jdkrTx`| D ] \}}||f|�|�}|||< q.W n6x4| jD ]*}| j||d�} || f|�|�}|||< q\W | j j} |jd| j } | j j || | d�} | jdkr�| j } | S )Nr] zNumber of keys must be 1r )r` )r\ rd ) rf rg r� r" r} r� Z get_groupr� �axesr` ra r� ) r= rV rW rX r` ro r; rn ZfresZgrp_dfr� Zother_axr� r> r> r? r! H s$ z!DataFrameGroupBy._aggregate_framec O st | j }i }xPt|�D ]D\}}|jd d �|f }t||| j| jd�} | j|f|�|�||< qW | j�|�} |j | _ | S )N)� selectionrf r+ ) r" r� r rM rf r+ rr r` ra rd ) r= rV rW rX r` ro �i�itemr� Zcolgr� r> r> r? �_aggregate_item_by_itemc s z(DataFrameGroupBy._aggregate_item_by_itemFc C s t |�dkr:| jj| jj|jd�}|j|j�� dd�}|S t t j |� d �}|d kr\| j�� S t |t �rv| j|||d�S | jr�| jjnd }t |tjtf�r�| jj||| jd�S t |t�s�| jr�| jj||d�S | jj||| jgd�}| �|� |S n| �|||||�S d S )Nr )r\ rd F)r� )r� )r\ r; )r\ )r� r` ra rf r� rd r� Zdtypes�to_dictr� re Znot_nonerb r) r� r& r� Zndarrayr1 �_constructor_slicedZ _selectionr4 r' �_wrap_applied_output_series)r= rn r~ r� r� ro �first_not_none� key_indexr> r> r? r� w s. z%DataFrameGroupBy._wrap_applied_outputz list[Series]r )r� r� rN c sn |� � }tf dti|��� � fdd�|D �}tdd� |D ��}| jr�| j�| j�}t|�dkof|j dk} | r�|d |d _ | j |||d�S |r�dd l m } | |�S |s�| j ||d d�S t�d d� |D ��} | jdk�r |} |j�� } | j d k�r,d d � |D �}t|�dk�r,t|�d | _ n|j} |} | j} | jtk�r@| �� } | jj| | | d�}| j�sd| �|� | �|�S )Nr^ c s g | ]}|d k r|n� �qS )Nr> )ru rv )�backupr> r? rx � s z@DataFrameGroupBy._wrap_applied_output_series.<locals>.<listcomp>c s s | ] }|j V qd S )N)r\ )ru rv r> r> r? rw � s z?DataFrameGroupBy._wrap_applied_output_series.<locals>.<genexpr>r] r )r� )r{ Tc S s g | ]}t �|��qS r> )r� Zasarray)ru �vr> r> r? rx � s c S s h | ] }|j �qS r> )r; )ru rB r> r> r? � <setcomp>� s z?DataFrameGroupBy._wrap_applied_output_series.<locals>.<setcomp>)r\ rd )Z_construct_axes_dictr( rm r3 �squeezerO � _get_axisr} r� r% r; r� r� r{ r� Zvstackr\ r� rt r� r� �tolistr` ra r& r' r� )r= r~ r� r� r? r@ rX Zall_indexed_sameZ applied_indexZsingular_seriesr{ Zstacked_valuesr\ rd rl ro r> )rA r? r> � sB z,DataFrameGroupBy._wrap_applied_output_seriesTr )r� r� r} rN c s� |dks t ���� }|r$|jdd�}ddd�� ��fdd� }|j|dd �}|�d |jd � t|�t|�k r�tjd t ��j � d � � d � � d�t dd� �j � |�}�jd kr�|j}|S )Nr F)r� r )�bvaluesrN c s �j jd| � df��S )Nr� r] )rf r� )rG )r� rX r= r> r? �arr_func� s z4DataFrameGroupBy._cython_transform.<locals>.arr_funcT)r, r] z Dropping invalid columns in r� zQ is deprecated. In a future version, a TypeError will be raised. Before calling .zJ, select only columns which should be valid for the transforming function.r- )r. )r� r/ r0 r1 �set_axisr7 r� r2 r3 r� rD r4 r` ra r} r� ) r= r� r� r} rX �mgrrH Zres_mgrr� r> )r� rX r= r? r� � s z"DataFrameGroupBy._cython_transformc O s� ddl m} g }| j}| jj|| jd�}| j|f|�|�\}} �x |D �]\} } t�| d| � y| � || | �\} } W nJ t k r� | � ||�S t k r� } zd}t |�|�W d d }~X Y nX t | t��rTt�| j�s�qFnl| j�|j��r|| gt| j� dd�}| j|_| j|_n2| jjt�| jgt| j� ��| j�| j| jd�}|�|� qF|�| � qFW | jdk�rt|jn|j}| jdk�r�dnd}||| jdd �}|j ||dd �}| � |�S ) Nr )r{ )r} r; z3transform must return a scalar value for each groupr] )rd r\ F)r} r� )r} r� ) r� r{ r" rf � get_iteratorr} � _define_pathsrm r� � _choose_pathr� �_transform_item_by_itemr� rb r4 r� �prod�shaper\ �is_r� rd r` ra Z concatenater� �reshaper� r� r� )r= rV rW rX r{ Zappliedr` �gen� fast_path� slow_pathr; r� �pathr� r� �msg�rZ concat_indexZ other_axisr� r> r> r? r� sB z#DataFrameGroupBy._transform_general)r< c O s | j |f|�||d�|��S )N)rZ r[ )r� )r= rV rZ r[ rW rX r> r> r? r� J s zDataFrameGroupBy.transformc C s t |t�o|j�| jj�S )N)rb r) rd �equalsr" )r= ro r> r> r? r� Q s z(DataFrameGroupBy._can_use_transform_fast)ro rN c C s@ | j }| jj\}}}|j| jjdd�}|j|dd�}|j|_|S )z6 Fast transform path for aggregations F)r� r )r} )r" rf r� r� r� r� r\ )r= ro r` r� r� r� r> r> r? r� V s z,DataFrameGroupBy._wrap_transform_fast_resultc sX t �t�r.� ��fdd�}� ���fdd�}n"� ��fdd�}� ���fdd�}||fS )Nc s t | ��� ��S )N)rB )r� )rW rV rX r> r? r� e r� z0DataFrameGroupBy._define_paths.<locals>.<lambda>c s | j � ��fdd��jd�S )Nc s t | ��� ��S )N)rB )rv )rW rV rX r> r? r� g r� zBDataFrameGroupBy._define_paths.<locals>.<lambda>.<locals>.<lambda>)r} )rU r} )r� )rW rV rX r= r> r? r� f s c s �| f� ���S )Nr> )r� )rW rV rX r> r? r� j r� c s | j � ��fdd��jd�S )Nc s �| f� ���S )Nr> )rv )rW rV rX r> r? r� l r� zBDataFrameGroupBy._define_paths.<locals>.<lambda>.<locals>.<lambda>)r} )rU r} )r� )rW rV rX r= r> r? r� k s )rb r: )r= rV rW rX rT rU r> )rW rV rX r= r? rL c s z DataFrameGroupBy._define_paths)rT rU r� c C s� |}||�}y ||�}W n, t k r. � Y n tk rD ||fS X t|t�sX||fS |j�|j�sn||fS |�|�r||}||fS )N)r� � Exceptionrb r) rd rY )r= rT rU r� rV r� Zres_fastr> r> r? rM p s z DataFrameGroupBy._choose_path)r` rN c C s� i }g }x�t |�D ]~\}}|jd d �|f }t||| j| jd�}y|�|�||< W n2 tk r� tjdt | �j � d�t dd� Y qX |� |� qW |s�td��|j �|�} | jj||jd�} | | _ | S )N)r8 rf r+ z Dropping invalid columns in z�.transform is deprecated. In a future version, a TypeError will be raised. Before calling .transform, select only columns which should be valid for the transforming function.� )r. z)Transform function invalid for data types)r\ )r� r rM rf r+ r� r� r2 r3 r� rD r4 r� rd r� r` ra r\ ) r= r` r� r� Zindsr9 �col�subset�sgbrd ro r> r> r? rN � s. z(DataFrameGroupBy._transform_item_by_itemc O s� g }| j }| jj|| jd�}x�|D ]�\}} t�| d|� || f|�|�} y | �� } W n tk rh Y nX t| �s�t | �r�t | �r�| r�t | �r�|� | � |�� q"tdt| �j� d���q"W | �||�S )a1 Return a copy of a DataFrame excluding filtered elements. Elements from groups are filtered if they do not satisfy the boolean criterion specified by func. Parameters ---------- func : function Function to apply to each subframe. Should return True or False. dropna : Drop groups that do not pass the filter. True by default; If False, groups that evaluate False are filled with NaNs. Returns ------- filtered : DataFrame Notes ----- Each subframe is endowed the attribute 'name' in case you need to know which group you are working on. Functions that mutate the passed object can produce unexpected behavior or errors and are not supported. See :ref:`gotchas.udf-mutation` for more details. Examples -------- >>> df = pd.DataFrame({'A' : ['foo', 'bar', 'foo', 'bar', ... 'foo', 'bar'], ... 'B' : [1, 2, 3, 4, 5, 6], ... 'C' : [2.0, 5., 8., 1., 2., 9.]}) >>> grouped = df.groupby('A') >>> grouped.filter(lambda x: x['B'].mean() > 3.) A B C 1 bar 2 5.0 3 bar 4 1.0 5 bar 6 9.0 )r} r; zfilter function returned a z , but expected a scalar bool)rO rf rK r} rm r� rD �AttributeErrorr r r r r� r� r� r� rD r� ) r= rV r� rW rX r� r` rS r; r� r� r> r> r? r� � s ( zDataFrameGroupBy.filterz DataFrameGroupBy | SeriesGroupByc sD | j dkrtd��t|t�r8t|�dkr8tjdtdd� t� � |�S )Nr] z'Cannot subset columns when using axis=1zmIndexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.� )r. ) r} r� rb rs r� r2 r3 r4 rT � __getitem__)r= r| )rY r> r? ra � s z DataFrameGroupBy.__getitem__)r� c C s� |dkrR|dkr| j }t|| j| j| j| j| j|| j| j| j| j | j | j | j d�S |dkr�|dkrl| j | }t || j| j|| j| j| j | j | j d� S td��dS )a sub-classes to define return a sliced object Parameters ---------- key : string / list of selections ndim : {1, 2} requested ndim of result subset : object, default None subset to act on r` N) r} r rf r+ r8 r& r� � group_keysrD r� �mutatedr� r] )r rf r8 r� rb rD r� r� zinvalid ndim for _gotitem)r` r rf r} r r+ r& r� rb rD r� rc r� rM r� )r= r| r� r] r> r> r? �_gotitem s@ zDataFrameGroupBy._gotitemr c C s" | j }| jdkr|jjS |jS d S )Nr] )r" r} r� r� )r= r` r> r> r? r/ 5 s z'DataFrameGroupBy._get_data_to_aggregate�Nonec C sd |j }xXtt| jj�t| j�� �tdd� | jjD ���D ]$\}}}|r8||kr8|�d||� q8W d S )Nc S s g | ] }|j �qS r> )�in_axis)ru �grpr> r> r? rx B s zCDataFrameGroupBy._insert_inaxis_grouper_inplace.<locals>.<listcomp>r )rd r� �reversedrf rl Zget_group_levelsr �insert)r= ro rd r; r rf r> r> r? r' < s " z/DataFrameGroupBy._insert_inaxis_grouper_inplacez+Mapping[base.OutputKey, Series | ArrayLike])r� rN c C s� dd� |� � D �}tdd� |D ��}|�| j�d| j �j� | j�|�}||_ | j sj| � |� |� � }n | j j|_| jdkr�|j}|j�| jj�r�| jj�� |_| �|�S )a Wraps the output of DataFrameGroupBy aggregations into the expected result. Parameters ---------- output : Mapping[base.OutputKey, Union[Series, np.ndarray]] Data to wrap. Returns ------- DataFrame c S s i | ]\}}||j �qS r> )rz )ru r| r r> r> r? r� Y s z<DataFrameGroupBy._wrap_aggregated_output.<locals>.<dictcomp>c S s g | ] }|j �qS r> )ry )ru r| r> r> r? rx Z s z<DataFrameGroupBy._wrap_aggregated_output.<locals>.<listcomp>r] )r� r1 r# r" rE r} rl r` ra rd r& r' � _consolidaterf r� r\ r� rY r� r� )r= r� r� rd ro r> r> r? r� I s z(DataFrameGroupBy._wrap_aggregated_outputc C sz dd� |� � D �}| j�|�}| jdkr:|j}| jj|_n2tdd� |D ��}|�| j�d| j �j � ||_| jj |_ |S )a( Wraps the output of DataFrameGroupBy transformations into the expected result. Parameters ---------- output : Mapping[base.OutputKey, Union[Series, np.ndarray, ExtensionArray]] Data to wrap. Returns ------- DataFrame c S s i | ]\}}||j �qS r> )rz )ru r| r r> r> r? r� ~ s z=DataFrameGroupBy._wrap_transformed_output.<locals>.<dictcomp>r] c s s | ] }|j V qd S )N)ry )ru r| r> r> r? rw � s z<DataFrameGroupBy._wrap_transformed_output.<locals>.<genexpr>) r� r` ra r} r� rd r1 r# rE rl r\ )r= r� r� ro rd r> r> r? r� o s z)DataFrameGroupBy._wrap_transformed_output)rJ rN c C s� | j sZ|jd dkr |jd nd}tt|��}|�d|� | j�|�}| �|� |�� }n | j j }|�d|� | j�|�}| j dkr�|j }| � |�jdd�S )Nr r] T)r )r& rP r1 r$ rI r` ra r' rj rf r� r} r� r� r( )r= rJ �rowsr\ ro r> r> r? r5 � s z$DataFrameGroupBy._wrap_agged_managerr )r` c c sD x>t |j�D ]0\}}|t|jd d �|f || j| jd�fV q W d S )N)r8 rf r+ )r� rd rM r rf r+ )r= r` r9 Zcolnamer> r> r? �_iterate_column_groupbys� s z)DataFrameGroupBy._iterate_column_groupbysc sV ddl m} |j}� fdd�| �|�D �}t|�sDtg || jjd�S |||dd�S d S )Nr )r{ c s g | ]\}}� |��qS r> r> )ru r� Z col_groupby)rV r> r? rx � s z>DataFrameGroupBy._apply_to_column_groupbys.<locals>.<listcomp>)rd r\ r] )r~ r} )r� r{ rd rl r� r) rf r� )r= rV r` r{ rd r� r> )rV r? �_apply_to_column_groupbys� s z*DataFrameGroupBy._apply_to_column_groupbysc sr | � � }| jj\� }�� dk�ddd�� ��fdd� }|�|�}t�| dd�� | �|�}W dQ R X | j|d d �S ) z� Compute count of group, excluding missing values. Returns ------- DataFrame Count of values within each group. r� r )rG rN c sF | j dkr"�t| ��dd� @ }n�t| � @ }tj|� �dd�}|S )Nr] r� )�labelsZmax_binr} )r� r rR r Zcount_level_2d)rG ZmaskedZcounted)r� r� r r> r? �hfunc� s z%DataFrameGroupBy.count.<locals>.hfuncr� TNr )r� )r/ rf r� r1 re Z temp_setattrr5 r� )r= rn r� ro r6 ro r> )r� r� r r? r � s zDataFrameGroupBy.count)r� rN c s^ | j dkr | �� fdd��S | j}| j� fdd�|d�}| jsZttt|���|_| � |� |S )a� Return DataFrame with counts of unique elements in each position. Parameters ---------- dropna : bool, default True Don't include NaN in the counts. Returns ------- nunique: DataFrame Examples -------- >>> df = pd.DataFrame({'id': ['spam', 'egg', 'egg', 'spam', ... 'ham', 'ham'], ... 'value1': [1, 5, 5, 2, 5, 5], ... 'value2': list('abbaxy')}) >>> df id value1 value2 0 spam 1 a 1 egg 5 b 2 egg 5 b 3 spam 2 a 4 ham 5 x 5 ham 5 y >>> df.groupby('id').nunique() value1 value2 id egg 1 1 ham 1 2 spam 2 1 Check for rows with the same id but conflicting values: >>> df.groupby('id').filter(lambda g: (g.nunique() > 1).any()) id value1 value2 0 spam 1 a 3 spam 2 a 4 ham 5 x 5 ham 5 y r c s | � � �S )N)r� )r^ )r� r> r? r� r� z*DataFrameGroupBy.nunique.<locals>.<lambda>c s | � � �S )N)r� )r^ )r� r> r? r� r� )r` ) r} rh r" rm r& r1 r$ r� r\ r' )r= r� r` r� r> )r� r? r� � s - zDataFrameGroupBy.nunique)�skipnac s8 t �� �� � dkrd nd�� ��fdd�}| �|| j�S )Nr Fc sH | j tjd���d�}|j}| ���� � fdd�|D �}| j||jd�S )NZargmax)r} rp r� c s" g | ]}|d kr� | nt j�qS )r )r� �nan)ru r9 )r\ r> r? rx & s z9DataFrameGroupBy.idxmax.<locals>.func.<locals>.<listcomp>)r\ )�_reducer" Z nanargmaxr� rE r= r\ )�dfr� r� ro )r} r� rp )r\ r? rV s z%DataFrameGroupBy.idxmax.<locals>.func)r) �_get_axis_number�_python_apply_generalr" )r= r} rp rV r> )r} r� rp r? �idxmax s zDataFrameGroupBy.idxmaxc s8 t �� �� � dkrd nd�� ��fdd�}| �|| j�S )Nr Fc sH | j tjd���d�}|j}| ���� � fdd�|D �}| j||jd�S )NZargmin)r} rp r� c s" g | ]}|d kr� | nt j�qS )r )r� rq )ru r9 )r\ r> r? rx ; s z9DataFrameGroupBy.idxmin.<locals>.func.<locals>.<listcomp>)r\ )rr r" Z nanargminr� rE r= r\ )rs r� r� ro )r} r� rp )r\ r? rV 0 s z%DataFrameGroupBy.idxmin.<locals>.func)r) rt ru r" )r= r} rp rV r> )r} r� rp r? �idxmin+ s zDataFrameGroupBy.idxmin)N)r� )F)Tr )T)N)T)r T)r T)0rD r r r+ �dataframe_apply_allowlistr r r r r- rr r rP r� r! r; r� r> r� r� r r r/ r� r� r� rL rM rN r� ra rd r/ r' r� r� r5 rl rm r r� r) rv rC rw r6 Zboxplotr r> r> )rY r? r k sN Q J' .L'2 % D1 & "< r )_rC � __future__r � collectionsr r � functoolsr �textwrapr �typingr r r r r r r r2 �numpyr� Z pandas._libsr r r� Zpandas._typingr r r r Zpandas.util._decoratorsr r r Zpandas.core.dtypes.commonr r r r r r r r Zpandas.core.dtypes.missingr r Z pandas.corer! r" Zpandas.core.aggregationr# r$ r% Zpandas.core.applyr& Zpandas.core.baser' Zpandas.core.common�core�commonre Zpandas.core.constructionr( Zpandas.core.framer) Zpandas.core.genericr* Zpandas.core.groupbyr+ Zpandas.core.groupby.groupbyr, r- r. r/ r0 Zpandas.core.indexes.apir1 r2 r3 Zpandas.core.seriesr4 Zpandas.core.util.numba_r5 Zpandas.plottingr6 r7 r: Z AggScalarr9 rF rL r rM rx r r> r> r> r? �<module> sP $ ( $ N
| ver. 1.4 |
Github
|
.
| PHP 8.3.23 | Генерация страницы: 0.07 |
proxy
|
phpinfo
|
Настройка